{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:SAHKLTD2WSHH2VISM3RXJXB2U6","short_pith_number":"pith:SAHKLTD2","schema_version":"1.0","canonical_sha256":"900ea5cc7ab48e7d551266e374dc3aa78732826d2d83db5816e4b3fb4984c416","source":{"kind":"arxiv","id":"2506.23491","version":3},"attestation_state":"computed","paper":{"title":"ZonUI-3B: A Lightweight Vision-Language Model for Cross-Resolution GUI Grounding","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"ShengJing Yang, Tzer-Jen Wei, ZongHan Hsieh","submitted_at":"2025-06-30T03:33:02Z","abstract_excerpt":"In this paper, we present ZonUI-3B, a lightweight Vision-Language Model (VLM) that can be fully trained on a single consumer-grade GPU (RTX 4090) while delivering performance comparable to significantly larger models on GUI grounding tasks. The model incorporates several key innovations: (i) combine cross-platform, multi-resolution dataset of 24K examples from diverse sources including mobile, desktop, and web GUI screenshots to effectively address data scarcity in high-resolution desktop environments; (ii) a two-stage fine-tuning strategy, where initial cross-platform training establishes rob"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2506.23491","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-30T03:33:02Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"ff1b08f3ed01bf7a59af9fe1446e9d94adaf2886a5ac4951616289e59218aa3a","abstract_canon_sha256":"9e8b42bca5d26b6ab788736bf58aa6bb0962e92ee7b4f313746d2f55e22728ff"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:39:12.615480Z","signature_b64":"SWgNErzmT9AJr2TsnTxcgRd0MrSsrMz9y61vqhuEBQHAgmvudk+lcoWt2sJqZodZeZwAglAQNSTFic5AB6frCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"900ea5cc7ab48e7d551266e374dc3aa78732826d2d83db5816e4b3fb4984c416","last_reissued_at":"2026-07-05T11:39:12.614972Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:39:12.614972Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ZonUI-3B: A Lightweight Vision-Language Model for Cross-Resolution GUI Grounding","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"ShengJing Yang, Tzer-Jen Wei, ZongHan Hsieh","submitted_at":"2025-06-30T03:33:02Z","abstract_excerpt":"In this paper, we present ZonUI-3B, a lightweight Vision-Language Model (VLM) that can be fully trained on a single consumer-grade GPU (RTX 4090) while delivering performance comparable to significantly larger models on GUI grounding tasks. The model incorporates several key innovations: (i) combine cross-platform, multi-resolution dataset of 24K examples from diverse sources including mobile, desktop, and web GUI screenshots to effectively address data scarcity in high-resolution desktop environments; (ii) a two-stage fine-tuning strategy, where initial cross-platform training establishes rob"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.23491","kind":"arxiv","version":3},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2506.23491/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2506.23491","created_at":"2026-07-05T11:39:12.615025+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.23491v3","created_at":"2026-07-05T11:39:12.615025+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.23491","created_at":"2026-07-05T11:39:12.615025+00:00"},{"alias_kind":"pith_short_12","alias_value":"SAHKLTD2WSHH","created_at":"2026-07-05T11:39:12.615025+00:00"},{"alias_kind":"pith_short_16","alias_value":"SAHKLTD2WSHH2VIS","created_at":"2026-07-05T11:39:12.615025+00:00"},{"alias_kind":"pith_short_8","alias_value":"SAHKLTD2","created_at":"2026-07-05T11:39:12.615025+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SAHKLTD2WSHH2VISM3RXJXB2U6","json":"https://pith.science/pith/SAHKLTD2WSHH2VISM3RXJXB2U6.json","graph_json":"https://pith.science/api/pith-number/SAHKLTD2WSHH2VISM3RXJXB2U6/graph.json","events_json":"https://pith.science/api/pith-number/SAHKLTD2WSHH2VISM3RXJXB2U6/events.json","paper":"https://pith.science/paper/SAHKLTD2"},"agent_actions":{"view_html":"https://pith.science/pith/SAHKLTD2WSHH2VISM3RXJXB2U6","download_json":"https://pith.science/pith/SAHKLTD2WSHH2VISM3RXJXB2U6.json","view_paper":"https://pith.science/paper/SAHKLTD2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.23491&json=true","fetch_graph":"https://pith.science/api/pith-number/SAHKLTD2WSHH2VISM3RXJXB2U6/graph.json","fetch_events":"https://pith.science/api/pith-number/SAHKLTD2WSHH2VISM3RXJXB2U6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SAHKLTD2WSHH2VISM3RXJXB2U6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SAHKLTD2WSHH2VISM3RXJXB2U6/action/storage_attestation","attest_author":"https://pith.science/pith/SAHKLTD2WSHH2VISM3RXJXB2U6/action/author_attestation","sign_citation":"https://pith.science/pith/SAHKLTD2WSHH2VISM3RXJXB2U6/action/citation_signature","submit_replication":"https://pith.science/pith/SAHKLTD2WSHH2VISM3RXJXB2U6/action/replication_record"}},"created_at":"2026-07-05T11:39:12.615025+00:00","updated_at":"2026-07-05T11:39:12.615025+00:00"}